L-PBF High-Throughput Data Pipeline Approach for Multi-modal Integration
Integrating Materials and Manufacturing Innovation · 2024-09 · 13 (3) · 758-772
DOI: 10.1007/s40192-024-00368-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Integrating Materials and Manufacturing Innovation, online erschienen am 19.07.2024. Verfasst von Kristen J. Hernandez und 11 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Energy’s National Nuclear Security Administration.
Abstract (Originalsprache)
Metal-based additive manufacturing requires active monitoring solutions for assessing part quality. Multiple sensors and data streams, however, generate large heterogeneous data sets that are impractical for manual assessment and characterization. In this work, an automated pipeline is developed that enables feature extraction from high-speed camera video and multi-modal data analysis. The framework removes the need for manual assessment through the utilization of deep learning techniques and training models in a weakly supervised paradigm. We demonstrate this pipeline’s capability over 700,000 high-speed camera frames. The pipeline successfully extracts melt pool and spatter geometries and links them to corresponding pyrometry, radiography, and processparameter information. 715 individual prints are examined to reveal melt pool areas that exceeds 0.07 mm 2 and pyrometry signal over a threshold (375 pyrometry units) were more likely to have defects. These automated processes enable massive throughput of characterization techniques.
Förderung
- Department of Energy’s National Nuclear Security Administration
Zitieren
APA
Hernandez, K. J., Ciardi, T. G., Yamamoto, R., Lu, M., Nihar, A., Jimenez, J. C., Tripathi, P. K., Giera, B., Forien, J., Lewandowski, J. J., French, R. H., & Bruckman, L. S. (2024). L-PBF High-Throughput Data Pipeline Approach for Multi-modal Integration. Integrating Materials and Manufacturing Innovation, 13(3), 758-772. https://doi.org/10.1007/s40192-024-00368-0
Vancouver
Hernandez KJ, Ciardi TG, Yamamoto R, Lu M, Nihar A, Jimenez JC, et al. L-PBF High-Throughput Data Pipeline Approach for Multi-modal Integration. Integrating Materials and Manufacturing Innovation. 2024;13(3):758-772. doi:10.1007/s40192-024-00368-0
BibTeX
@article{Hernandez2024,
author = {Hernandez, Kristen J. and Ciardi, Thomas G. and Yamamoto, Rachel and Lu, Mingjian and Nihar, Arafath and Jimenez, Jayvic Cristian and Tripathi, Pawan K. and Giera, Brian and Forien, Jean-Baptiste and Lewandowski, John J. and French, Roger H. and Bruckman, Laura S.},
title = {L-PBF High-Throughput Data Pipeline Approach for Multi-modal Integration},
journal = {Integrating Materials and Manufacturing Innovation},
year = {2024},
volume = {13},
number = {3},
pages = {758--772},
doi = {10.1007/s40192-024-00368-0}
}
EUVIMED